Drivers' fatigue detection using image sensors

• Main Author: Siti Nadya Redzwan
• Other Authors: Wang Han
• Format: Final Year Project
• Language: English
• Published: Nanyang Technological University 2020
• Subjects: Engineering::Electrical and electronic engineering
• Online Access: https://hdl.handle.net/10356/139985
• Institution: Nanyang Technological University

The increasing number of accidents on the road each day is worrying. There are various reasons that lead to accidents but fatigue and drowsiness are the major causes of accidents. It is essential to detect drivers’ fatigue to prevent from more accidents happening every day. In this project, a real time method through OpenCV Python from a video input and based on image processing algorithms for fatigue detection is presented. Various methods are implemented to develop the fatigue detection such as the use of Haar Cascade Classifier and Facial Landmarks for Dlib;s library. The fatigue detection consists of several detection methods like face detection, eye detection and mouth detection. The use of infrared camera is also involved to detect facial features in low lighting conditions. An alarm will be triggered when the conditions for eye closure and yawn detection are satisfied. The proposed algorithm will be explained and elaborated in Chapter 4. The implementation of fatigue detection in night vision is vital in ensuring the safety of all road users. Hence, the fatigue detection will be able to function in low lighting conditions such as at night. The accuracy and reliability of the fatigue detection will be analysed with various experiments tested.